Joint Content Caching and Request Routing for User-Centric Many-Objective Metaverse Services

IF 6.7 2区计算机科学 Q1 ENGINEERING, MULTIDISCIPLINARY

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-13 DOI:10.1109/TNSE.2025.3541746

Zhaoming Hu;Chao Fang;Zhuwei Wang;Jining Chen;Shu-Ming Tseng;Mianxiong Dong

{"title":"Joint Content Caching and Request Routing for User-Centric Many-Objective Metaverse Services","authors":"Zhaoming Hu;Chao Fang;Zhuwei Wang;Jining Chen;Shu-Ming Tseng;Mianxiong Dong","doi":"10.1109/TNSE.2025.3541746","DOIUrl":null,"url":null,"abstract":"Metaverse, as a revolutionary technology that changes the way of human interaction, brings new challenges to content delivery services due to the extensive data transmission and personalized service requirements. To ensure a personalized user experiences while improving the utilization of heterogeneous network resources, a user-centric many-objective metaverse content delivery framework is proposed to optimize content delivery through user attention awareness. This framework addresses two key subproblems in metaverse content delivery by investigating user-centric many-objective cooperative content caching and deep reinforcement learning (DRL)-based request routing. The user-centric many-objective cooperative content caching is proposed to dynamically combine three basic preference prediction results to predict user preferences and control network resource allocation, which can simultaneously optimize prediction precision, delay, offloaded traffic, and load balancing. In DRL-based request routing, the reward function is designed to enable the optimization of multiple objectives. The multi-objective DRL routing algorithm is employed to continuously observe network states and make adaptive routing decisions in response to user requests. In the simulation, a movie dataset is employed to simulate user requests and support user attention awareness. The results show that the proposed content delivery framework outperforms existing basic prediction algorithms and other content delivery algorithms on four evaluation indicators.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"1911-1925"},"PeriodicalIF":6.7000,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Network Science and Engineering","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10884929/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}

引用次数: 0

Abstract

Metaverse, as a revolutionary technology that changes the way of human interaction, brings new challenges to content delivery services due to the extensive data transmission and personalized service requirements. To ensure a personalized user experiences while improving the utilization of heterogeneous network resources, a user-centric many-objective metaverse content delivery framework is proposed to optimize content delivery through user attention awareness. This framework addresses two key subproblems in metaverse content delivery by investigating user-centric many-objective cooperative content caching and deep reinforcement learning (DRL)-based request routing. The user-centric many-objective cooperative content caching is proposed to dynamically combine three basic preference prediction results to predict user preferences and control network resource allocation, which can simultaneously optimize prediction precision, delay, offloaded traffic, and load balancing. In DRL-based request routing, the reward function is designed to enable the optimization of multiple objectives. The multi-objective DRL routing algorithm is employed to continuously observe network states and make adaptive routing decisions in response to user requests. In the simulation, a movie dataset is employed to simulate user requests and support user attention awareness. The results show that the proposed content delivery framework outperforms existing basic prediction algorithms and other content delivery algorithms on four evaluation indicators.

查看原文本刊更多论文

以用户为中心的多目标元宇宙服务的联合内容缓存和请求路由选择

元数据作为一种改变人类交互方式的革命性技术，其广泛的数据传输和个性化服务需求给内容分发服务带来了新的挑战。为了确保个性化的用户体验，同时提高异构网络资源的利用率，本文提出了一个以用户为中心的多目标元数据内容分发框架，通过用户注意力感知来优化内容分发。该框架通过研究以用户为中心的多目标合作内容缓存和基于深度强化学习（DRL）的请求路由，解决了元数据内容交付中的两个关键子问题。其中，以用户为中心的多目标协同内容缓存是通过动态组合三种基本偏好预测结果来预测用户偏好并控制网络资源分配，可同时优化预测精度、延迟、卸载流量和负载均衡。在基于 DRL 的请求路由中，奖励函数的设计实现了多目标优化。多目标 DRL 路由算法用于持续观察网络状态，并根据用户请求做出自适应路由决策。在仿真中，采用了电影数据集来模拟用户请求并支持用户注意力感知。结果表明，在四个评价指标上，所提出的内容交付框架优于现有的基本预测算法和其他内容交付算法。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE Transactions on Network Science and Engineering Engineering-Control and Systems Engineering

CiteScore

12.60

自引率

9.10%

发文量

393

期刊介绍： The proposed journal, called the IEEE Transactions on Network Science and Engineering (TNSE), is committed to timely publishing of peer-reviewed technical articles that deal with the theory and applications of network science and the interconnections among the elements in a system that form a network. In particular, the IEEE Transactions on Network Science and Engineering publishes articles on understanding, prediction, and control of structures and behaviors of networks at the fundamental level. The types of networks covered include physical or engineered networks, information networks, biological networks, semantic networks, economic networks, social networks, and ecological networks. Aimed at discovering common principles that govern network structures, network functionalities and behaviors of networks, the journal seeks articles on understanding, prediction, and control of structures and behaviors of networks. Another trans-disciplinary focus of the IEEE Transactions on Network Science and Engineering is the interactions between and co-evolution of different genres of networks.